Centre de documentation
scientifique

Dépouillements

Semisupervised one-class support vector machine for classification of remote sensing data / Jordi Munoz-Mari in IEEE Transactions on geoscience and remote sensing, vol 48 n° 8 (August 2010)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 48 n° 8 (August 2010) . - pp 3188 - 3197 Titre : Semisupervised one-class support vector machine for classification of remote sensing data Type de document : Article/Communication Auteurs : Jordi Munoz-Mari, Auteur ; Francesca Bovolo, Auteur ; et al., Auteur Année de publication : 2010 Article en page(s) : pp 3188 - 3197 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage semi-dirigé [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] classification semi-dirigée [Termes IGN] détection de changement [Termes IGN] détection de cible Résumé : (Auteur) This paper presents two semisupervised one-class support vector machine (OC-SVM) classifiers for remote sensing applications. In one-class image classification, one tries to detect pixels belonging to one of the classes in the image and reject the others. When few labeled pixels of only one class are available, obtaining a reliable classifier is a difficult task. In the particular case of SVM-based classifiers, this task is even harder because the free parameters of the model need to be finely adjusted, but no clear criterion can be adopted. In order to improve the OC-SVM classifier accuracy and alleviate the problem of free-parameter selection, the information provided by unlabeled samples present in the scene can be used. In this paper, we present two state-of-the-art algorithms for semi-supervised one-class classification for remote sensing classification problems. The first proposed algorithm is based on modifying the OC-SVM kernel by modeling the data marginal distribution with the graph Laplacian built with both labeled and unlabeled samples. The second one is based on a simple modification of the standard SVM cost function which penalizes more the errors made when classifying samples of the target class. The good performance of the proposed methods is illustrated in four challenging remote sensing image classification scenarios where the goal is to detect one of the classes present on the scene. In particular, we present results for multisource urban monitoring, hyperspectral crop detection, multispectral cloud screening, and change-detection problems. Experimental results show the suitability of the proposed techniques, particularly in cases with few or poorly representative labeled samples. Numéro de notice : A2010-307 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2010.2045764 En ligne : https://doi.org/10.1109/TGRS.2010.2045764 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30501 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2010081	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Rule-based classification of a very high resolution image in an urban environment using multispectral segmentation by cartographic data / M. Bouziani in IEEE Transactions on geoscience and remote sensing, vol 48 n° 8 (August 2010)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 48 n° 8 (August 2010) . - pp 3198 - 3211 Titre : Rule-based classification of a very high resolution image in an urban environment using multispectral segmentation by cartographic data Type de document : Article/Communication Auteurs : M. Bouziani, Auteur ; Kalifa Goïta, Auteur ; D. He, Auteur Année de publication : 2010 Article en page(s) : pp 3198 - 3211 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] base de données localisées [Termes IGN] classification à base de connaissances [Termes IGN] détection de changement [Termes IGN] données cartographiques [Termes IGN] image à très haute résolution [Termes IGN] milieu urbain [Termes IGN] précision de la classification [Termes IGN] segmentation d'image Résumé : (Auteur) Classification algorithms based on single-pixel analysis often do not give the desired result when applied to high-spatial-resolution remote-sensing data. In such cases, classification algorithms based on object-oriented image segmentation are needed. There are many segmentation algorithms in the literature, but few have been applied in urban studies to classify a high-spatial-resolution remote-sensing image. Furthermore, the user must specify the spectral and spatial parameters that are data dependent. In this paper, we propose an automatic multispectral segmentation algorithm inspired by the specific idea of guiding a classification process for a high-spatial-resolution remote-sensing image of an urban area using an existing digital map of the same area. The classification results could be used, for example, for high-scale database updating or change-detection studies. The algorithm developed uses digital maps and spectral data as inputs. It generates the segmentation parameters automatically. The algorithm is able to provide a segmented image with accuracy greater than 90%. The segmentation results are then used in a rule-based classification using spectral, geometric, textural, and contextual information. The classification accuracy of the proposed rule-based classification is at least 17% greater than the maximum-likelihood classification results. Results and future improvements will be discussed. Numéro de notice : A2010-308 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2010.2044508 En ligne : https://doi.org/10.1109/TGRS.2010.2044508 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30502 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2010081	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Ionospheric response to the geomagnetic storm on august 21, 2003 over China using GNSS-based tomographic technique / D. Wen in IEEE Transactions on geoscience and remote sensing, vol 48 n° 8 (August 2010)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 48 n° 8 (August 2010) . - pp 3212 - 3217 Titre : Ionospheric response to the geomagnetic storm on august 21, 2003 over China using GNSS-based tomographic technique Type de document : Article/Communication Auteurs : D. Wen, Auteur ; Y. Yuan, Auteur ; J. Ou, Auteur ; K. Zhang, Auteur Année de publication : 2010 Article en page(s) : pp 3212 - 3217 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale [Termes IGN] Chine [Termes IGN] ionosphère [Termes IGN] perturbation ionosphérique [Termes IGN] positionnement par GNSS [Termes IGN] tempête magnétique [Termes IGN] tomographie Résumé : (Auteur) The impacts of the August 21, 2003 geomagnetic storm on the ionosphere over China have been first investigated by using the so-called computerized ionospheric tomography (CIT) technique and the observations of the Crustal Movement Observation Network of China. Tomographic results show that the main ionospheric effects of this geomagnetic storm over China are as follows: (1) the negative storm phase effect appears in the F region and (2) the positive storm phase effect occurs above the F region. Meanwhile, some key features in the ionospheric structure have been revealed in the ionospheric images during the storm; this includes the disturbances and an elongated region of the reduced electron density at the latitude around 32°N. Statistical comparisons are carried out to confirm the reliability of the global-navigation-satellite-system-based CIT reconstruction results using the profile obtained from ionosonde observations. Numéro de notice : A2010-309 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2010.2044579 En ligne : https://doi.org/10.1109/TGRS.2010.2044579 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30503 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2010081	RAB	Revue	Centre de documentation	En réserve L003	Disponible